Abstract
We study a multiscale tensor regularization based JPEG decompression artifact removal in digital images. Structure tensor eigenvalues based robust edge map is used within a variable exponent regularization. Variational constrained minimization which combines data fidelity driven by color subsampling and discrete cosine transformation operator is utilized. Experimental results across different compression levels and with various error metrics indicate our proposed method obtains high quality results on cartoon/clip-art and LIVE1 natural image databases.
This is a preview of subscription content, log in via an institution to check access.
Notes
ARCNN method was run on the Y component (luminance) of the image converted to the YCbCr color space, and remaining methods were run using corresponding vectorial versions.
Compare to results from ARCNN (Dong et al. 2015).
References
Alter, F., Durand, S., & Froment, J. (2005). Adapted total variation for artifact free decompression of jpeg images. Journal of Mathematical Imaging and Vision, 23(2), 199–211. https://doi.org/10.1007/s10851-005-6467-9.
Bredies, K., & Holler, M. (2012a). Artifact-free decompression and zooming of JPEG compressed images with total generalized variation. In VISIGRAPP (pp. 242–258). https://doi.org/10.1007/978-3-642-38241-3_16.
Bredies, K., & Holler, M. (2012b). A total variation-based JPEG decompression model. SIAM Journal on Imaging Sciences, 5(1), 366–393. https://doi.org/10.1137/110833531.
Comaniciu, D., & Meer, P. (2002). Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5), 603–619. https://doi.org/10.1109/34.1000236.
Dabov, K., Foi, A., Katkovnik, V., & Egiazarian, K. (2007). Image denoising by sparse 3D transform-domain collaborative filtering. IEEE Transactions on Image Processing, 16(8), 2080–2095. https://doi.org/10.1109/TIP.2007.901238.
Dong, C., Deng, Y., Loy, C. C., & Tang, C. (2015). Compression artifacts reduction by a deep convolutional network. In International conference on computer vision.
Karaca, A. C., & Güllü, M. K. (2019). Superpixel based recursive least-squares method for lossless compression of hyperspectral images. Multidimensional Systems and Signal Processing, 30(2), 903–919. https://doi.org/10.1007/s11045-018-0590-4.
Kulalvaimozhi, V., Alex, M. G., & Peter, S. J. (2019). A novel homomorphic encryption and an enhanced DWT (NHE-EDWT) compression of crop images in agriculture field. Multidimensional Systems and Signal Processing,. https://doi.org/10.1007/s11045-019-00660-9.
Pang, X., Zhang, S., Gu, J., Li, L., Liu, B., & Wang, H. (2015). Improved L0 gradient minimization with L1 fidelity for image smoothing. PLoS One,. https://doi.org/10.1371/journal.pone.0138682.
Prasath, V. B. S. (2011). A well-posed multiscale regularization scheme for digital image denoising. International Journal of Applied Mathematics and Computer Science, 21(4), 769–777. https://doi.org/10.2478/v10006-011-0061-7.
Prasath, V. B. S., Pelapur, R., Seetharaman, G., & Palaniappan, K. (2019). Multiscale structure tensor for improved feature extraction and image regularization. IEEE Transactions on Image Processing, 28(12), 6198–6210. https://doi.org/10.1109/TIP.2019.2924799.
Prasath, V. B. S., & Thanh, D. N. H. (2019). Structure tensor adaptive total variation for image restoration. Turkish Journal of Electrical Engineering and Computer Sciences, 27(2), 1147–1156. https://doi.org/10.3906/elk-1802-76.
Prasath, V. B. S., Thanh, D. N. H., & Hai, N. H. (2018a). On selecting the appropriate scale in image selective smoothing by nonlinear diffusion. In 7th International conference on communications and electronics (ICCE), Hue, Vietnam.
Prasath, V. B. S., Thanh, D. N. H., & Hai, N. H. (2018b). Regularization parameter selection in image restoration with inverse gradient: Single scale or multiscale? In 7th International conference on communications and electronics (ICCE), Hue, Vietnam.
Prasath, V. B. S., Thanh, D. N. H., Hai, N. H., & Cuong, N. X. (2017). Image restoration with total variation and iterative regularization parameter estimation. In: International symposium on information and communication technology (SoICT), Nha Trang, Vietnam (pp. 378–384). https://doi.org/10.1145/3155133.3155191.
Prasath, V. B. S., Vorotnikov, D., Pelapur, R., Jose, S., Seetharaman, G., & Palaniappan, K. (2015). Multiscale Tikhonov-total variation image restoration using spatially varying edge coherence exponent. IEEE Transactions on Image Processing, 24(12), 5220–5235. https://doi.org/10.1109/TIP.2015.2479471.
Rabbani, M. (2002). Jpeg 2000: Image compression fundamentals, standards and practice. Journal of Electronic Imaging, 11(2), 286. https://doi.org/10.1117/1.1469618.
Rudin, L., Osher, S., & Fatemi, E. (1992). Nonlinear total variation based noise removal algorithms. Physica D, 60(1–4), 259–268. https://doi.org/10.1016/0167-2789(92)90242-F.
Shen, M. Y., & Kuo, C. C. J. (1998). Review of postprocessing techniques for compression artifact removal. Journal of Visual Communication and Image Representation, 9(1), 2–14. https://doi.org/10.1006/jvci.1997.0378.
Thanh, D. N. H., Thanh, L. T., Hien, N. N., & Prasath, V. B. S. (2019). Adaptive total variation l1 regularization for salt and pepper image denoising. Optik,. https://doi.org/10.1016/j.ijleo.2019.163677.
Tomasi, C., & Manduchi, R. (1998). Bilateral filtering for gray and color images. In IEEE international conference on computer vision (pp. 59–66).
Wallace, G. K. (1992). The jpeg still picture compression standard. IEEE Transactions on Consumer Electronics, 38(1), 18–34. https://doi.org/10.1109/30.125072.
Wang, G., Wong, T. T., & Heng, P. A. (2006). Deringing cartoons by image analogies. ACM Transactions on Graphics, 25(4), 1360–1379. https://doi.org/10.1145/1183287.1183292.
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4), 600–612. https://doi.org/10.1109/TIP.2003.819861.
Xu, L., Lu, C., Xu, Y., & Jia, J. (2011). Image smoothing via L0 gradient minimization. ACM Transactions on Graphics, 30(6), 174:1–174:12. https://doi.org/10.1145/2070781.2024208.
Yim, C., & Bovik, A. C. (2011). Quality assessment of deblocked images. IEEE Transactions on Image Processing, 20(1), 88–98. https://doi.org/10.1109/TIP.2010.2061859.
Yim, C., & Ik Cho, N. (2005). Blocking artifact reduction method based on non-iterative POCS in the DCT domain. In IEEE international conference on image processing (ICIP) (Vol. 2, p. II-1022-5). https://doi.org/10.1109/ICIP.2005.1530232.
Zhang, Q., Xu, L., & Jia, J. (2014). 100+ times faster weighted median filter (WMF). In IEEE computer vision and pattern recognition (pp. 2830–2837). https://doi.org/10.1109/CVPR.2014.362.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Surya Prasath, V.B., Thanh, D.N.H., Hieu, L.M. et al. Compression artifacts reduction with multiscale tensor regularization. Multidim Syst Sign Process 32, 521–531 (2021). https://doi.org/10.1007/s11045-020-00747-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11045-020-00747-8